Probiotics for Antibiotic-Associated Diarrhoea (PAAD): a prospective observational study of antibiotic-associated diarrhoea (including Clostridium difficile-associated diarrhoea) in care homes

Background: Antibiotic prescribing rates in care homes are higher than in the general population. Antibiotics disrupt the normal gut flora, sometimes causing antibiotic-associated diarrhoea (AAD). Clostridium difficile (Hall and O'Toole 1935) Prevot 1938 is the most commonly identified cause of AAD. Little is known either about the frequency or type of antibiotics prescribed in care homes or about the incidence and aetiology of AAD in this setting. Objectives: The Probiotics for Antibiotic-Associated Diarrhoea (PAAD) study was designed as a two-stage study. PAAD stage 1 aimed to (1) prospectively describe antibiotic prescribing in care homes; (2) determine the incidence of C. difficile carriage and AAD (including C. difficile-associated diarrhoea); and (3) to consider implementation challenges and establish the basis for a sample size estimation for a randomised controlled trial (RCT) of probiotic administration with antibiotics to prevent AAD in care homes. If justified by PAAD stage 1, the RCT would be implemented in PAAD stage 2. However, as a result of new evidence regarding the clinical effectiveness of probiotics on the incidence of AAD, a decision was taken not to proceed with PAAD stage 2. Design: PAAD stage 1 was a prospective observational cohort study in care homes in South Wales with up to 12 months' follow-up for each resident. Setting: Recruited care homes had management and owner's agreement to participate and three or more staff willing to take responsibility for implementing the study. Participants: Eleven care homes were recruited, but one withdrew before any residents were recruited. A total of 279 care home residents were recruited to the observational study and 19 withdrew, 16 (84%) because of moving to a non-participating care home. Main outcome measures: The primary outcomes were the rate of antibiotic prescribing, incidence of AAD, defined as three or more loose stools (type 5-7 on the Bristol Stool Chart) in a 24-hour period, and C. difficile carriage confirmed on stool culture. Results: Stool samples were obtained at study entry from 81% of participating residents. Over half of the samples contained antibiotic-resistant isolates, with Enterobacteriaceae resistant to ciprofloxacin in 47%. Residents were prescribed an average of 2.16 antibiotic prescriptions per year [95% confidence interval (CI) 1.90 to 2.46]. Antibiotics were less likely to be prescribed to residents from dual-registered homes. The incidence of AAD was 0.57 (95% CI 0.41 to 0.81) episodes per year among those residents who were prescribed antibiotics. AAD was more likely in residents who were prescribed co-amoxiclav than other antibiotics and in those residents who routinely used incontinence pads. AAD was less common in residents from residential homes. Conclusions: Care home residents, particularly in nursing homes, are frequently prescribed antibiotics and often experience AAD. Antibiotic resistance, including ciprofloxacin resistance, is common in Enterobacteriaceae isolated from the stool of care home residents. Co-amoxiclav is associated with greater risk of AAD than other commonly prescribed antibiotics.